speckle-impl-connectors-overview
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and process objects from a Speckle server (see "ToHost Flow: [1. Fetch] --> Download objects from server" and the Power BI example calling Speckle.GetObjects("https://app.speckle.systems", ...)), which are user-published/untrusted models whose properties and proxies are parsed and used by the conversion/resolution pipeline, so third-party content can materially influence agent decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata